Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    sentences where the author is discussing preferences or giving anecdotal descriptions

    oai_token-act-pair · gemini-2.0-flash

    blog posts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    DoubleQuotes
    -0.77
    principalColumn
    -0.60
    ngdoc
    -0.60
    новништво
    -0.59
    '];?>
    -0.57
     disambiguazione
    -0.57
    }{*}{}
    -0.57
    BufferException
    -0.57
    XmlType
    -0.57
    ="#"><
    -0.57
    POSITIVE LOGITS
    dities
    0.47
     opportunity
    0.44
    Dislikes
    0.44
    ayashi
    0.41
     eagerly
    0.40
     interessiert
    0.40
    utnik
    0.40
    +#+#
    0.40
     Berto
    0.39
    хь
    0.39
    Act Density 2.824%

    No Known Activations